{"id":"https://openalex.org/W1978265849","doi":"https://doi.org/10.1108/00220410610688750","title":"Aggregation consistency and frequency of Chinese words and characters","display_name":"Aggregation consistency and frequency of Chinese words and characters","publication_year":2006,"publication_date":"2006-09-01","ids":{"openalex":"https://openalex.org/W1978265849","doi":"https://doi.org/10.1108/00220410610688750","mag":"1978265849"},"language":"en","primary_location":{"id":"doi:10.1108/00220410610688750","is_oa":false,"landing_page_url":"https://doi.org/10.1108/00220410610688750","pdf_url":null,"source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014123262","display_name":"Cl\u00e9ment Arsenault","orcid":"https://orcid.org/0000-0001-8404-0939"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Cl\u00e9ment Arsenault","raw_affiliation_strings":["\u00c9cole de biblioth\u00e9conomie et des sciences de l'information, Universit\u00e9 de Montr\u00e9al, Qu\u00e9bec, Canada","\u00c9cole de biblioth\u00e9conomie et des sciences de l\u2019information, Universit\u00e9 de Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole de biblioth\u00e9conomie et des sciences de l'information, Universit\u00e9 de Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"\u00c9cole de biblioth\u00e9conomie et des sciences de l\u2019information, Universit\u00e9 de Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014123262"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08151009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"62","issue":"5","first_page":"606","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9584000110626221,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9510999917984009,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.7771885395050049},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7517743706703186},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5711864829063416},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.4745886027812958},{"id":"https://openalex.org/keywords/vernacular","display_name":"Vernacular","score":0.4603421986103058},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.451416015625},{"id":"https://openalex.org/keywords/frequency-distribution","display_name":"Frequency distribution","score":0.44735419750213623},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4404976963996887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42917704582214355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42404115200042725},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.4137725234031677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41323989629745483},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41226693987846375},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4020977020263672},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39615029096603394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22482901811599731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.14008089900016785}],"concepts":[{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.7771885395050049},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7517743706703186},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5711864829063416},{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.4745886027812958},{"id":"https://openalex.org/C2780386941","wikidata":"https://www.wikidata.org/wiki/Q1036511","display_name":"Vernacular","level":2,"score":0.4603421986103058},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.451416015625},{"id":"https://openalex.org/C51921466","wikidata":"https://www.wikidata.org/wiki/Q1627586","display_name":"Frequency distribution","level":2,"score":0.44735419750213623},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4404976963996887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42917704582214355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42404115200042725},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4137725234031677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41323989629745483},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41226693987846375},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4020977020263672},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39615029096603394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22482901811599731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.14008089900016785},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/00220410610688750","is_oa":false,"landing_page_url":"https://doi.org/10.1108/00220410610688750","pdf_url":null,"source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W127041021","https://openalex.org/W202960689","https://openalex.org/W567258626","https://openalex.org/W577717896","https://openalex.org/W644009243","https://openalex.org/W1559964841","https://openalex.org/W1984066943","https://openalex.org/W1988294080","https://openalex.org/W2027963417","https://openalex.org/W2037959956","https://openalex.org/W2060603187","https://openalex.org/W2060864821","https://openalex.org/W2067570491","https://openalex.org/W2074413036","https://openalex.org/W2089753118","https://openalex.org/W2104981960","https://openalex.org/W2116294743","https://openalex.org/W2123672980","https://openalex.org/W4243381595","https://openalex.org/W4285719527","https://openalex.org/W6804690090"],"related_works":["https://openalex.org/W3123832408","https://openalex.org/W2090669199","https://openalex.org/W310149312","https://openalex.org/W137186961","https://openalex.org/W1598995231","https://openalex.org/W2964215859","https://openalex.org/W1724948991","https://openalex.org/W2611841097","https://openalex.org/W2246302223","https://openalex.org/W2041741339"],"abstract_inverted_index":{"Purpose":[0],"Aims":[1],"to":[2,20,36,123,135,169,212,227],"measure":[3],"syllable":[4,164],"aggregation":[5,38,86,94,131,165],"consistency":[6,39,87,132,152,237],"of":[7,15,45,54,127,138,184,201,210,240],"Romanized":[8,63,197,202,221,241],"Chinese":[9,46,176,242],"data":[10,90,129,139,222,235],"in":[11,182,208,223,244],"the":[12,23,50,66,69,79,115,141,160,205],"title":[13],"fields":[14],"bibliographic":[16,47,128,245],"records.":[17,246],"Also":[18],"aims":[19],"verify":[21],"if":[22],"term":[24,51],"frequency":[25,52,142,185],"distributions":[26,53,102,110,148],"satisfy":[27,103],"conventional":[28],"bibliometric":[29,147],"laws.":[30],"Design/methodology/approach":[31],"Uses":[32],"Cooper's":[33],"interindexer":[34],"formula":[35],"evaluate":[37],"within":[40,88,153],"and":[41,57,62,68,134,178,196,238],"between":[42,96,194],"two":[43,125,146],"sets":[44,126],"data.":[48,198],"Compares":[49],"polysyllabic":[55],"words":[56,177],"monosyllabic":[58],"characters":[59,179,203],"(for":[60,130],"vernacular":[61,195],"data)":[64],"with":[65,78],"Lotka":[67],"generalised":[70],"Zipf":[71],"theoretical":[72],"distributions.":[73],"The":[74,119,172,199],"fits":[75],"are":[76,121,149],"tested":[77],"Kolmogorov\u2010Smirnov":[80],"test.":[81],"Findings":[82],"Finds":[83],"high":[84],"internal":[85],"each":[89,154],"set":[91,137],"but":[92,106,187],"some":[93],"discrepancy":[95],"sets.":[97],"Shows":[98],"that":[99,107,175,188,220],"word":[100],"(polysyllabic)":[101],"Lotka's":[104,214],"law":[105],"character":[108],"(monosyllabic)":[109],"do":[111],"not":[112,167],"abide":[113],"by":[114],"law.":[116],"Research":[117],"limitations/implications":[118],"findings":[120],"limited":[122],"only":[124],"analysis)":[133],"one":[136],"for":[140],"distribution":[143,186,200,239],"analysis.":[144],"Only":[145],"tested.":[150],"Internal":[151],"database":[155],"remains":[156],"fairly":[157],"high.":[158],"Therefore":[159],"main":[161],"argument":[162],"against":[163],"does":[166],"appear":[168,226],"hold":[170],"true.":[171],"analysis":[173],"revealed":[174],"behave":[180],"differently":[181],"terms":[183,209],"there":[189],"is":[190],"no":[191],"noticeable":[192],"difference":[193],"exhibits":[204],"worst":[206],"case":[207],"fit":[211],"either":[213],"or":[215],"Zipf's":[216],"laws,":[217],"which":[218],"indicates":[219],"aggregated":[224],"form":[225],"be":[228],"a":[229],"preferable":[230],"option.":[231],"Originality/value":[232],"Provides":[233],"empirical":[234],"on":[236],"titles":[243]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}